[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-01-13 21:01:39 +08:00
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
--- a/tests/entrypoints/openai/responses/test_errors.py
+++ b/tests/entrypoints/openai/responses/test_errors.py
@@ -6,8 +6,8 @@ from unittest.mock import MagicMock

 import pytest

-from vllm.entrypoints.openai.protocol import ErrorResponse
-from vllm.entrypoints.openai.serving_engine import GenerationError, OpenAIServing
+from vllm.entrypoints.openai.engine.protocol import ErrorResponse
+from vllm.entrypoints.openai.engine.serving import GenerationError, OpenAIServing


@pytest.mark.asyncio